mindreader-mcp
Connects MindReader knowledge graph to MCP clients, enabling AI assistants with persistent memory and entity/relationship management.
README
MindReader MCP Server
Connect MindReader to Claude Code, Cursor, or any MCP-compatible client. Gives your AI assistant persistent memory backed by a knowledge graph.
Prerequisites
- MindReader V2 running locally (
npm start) - Node.js 18+
Install
git clone https://github.com/flu012/mindreader-mcp.git
cd mindreader-mcp
npm install
Setup with Claude Code
Add to your Claude Code settings (~/.claude/settings.json or project .claude/settings.json):
{
"mcpServers": {
"mindreader": {
"command": "node",
"args": ["/path/to/mindreader-mcp/src/index.js"],
"env": {
"MINDREADER_URL": "http://localhost:18900"
}
}
}
}
If MindReader has authentication enabled, add your token:
{
"mcpServers": {
"mindreader": {
"command": "node",
"args": ["/path/to/mindreader-mcp/src/index.js"],
"env": {
"MINDREADER_URL": "http://localhost:18900",
"MINDREADER_TOKEN": "your-api-token"
}
}
}
}
Setup with Cursor
Add to Cursor's MCP settings (~/.cursor/mcp.json):
{
"mcpServers": {
"mindreader": {
"command": "node",
"args": ["/path/to/mindreader-mcp/src/index.js"],
"env": {
"MINDREADER_URL": "http://localhost:18900"
}
}
}
}
Tools
| Tool | Description |
|---|---|
memory_search |
Search the knowledge graph for entities, facts, and relationships |
memory_store |
Store information using LLM preprocessing (auto-extracts entities) |
memory_create |
Create/update entities directly without LLM (precise control) |
memory_entities |
List entities in the knowledge graph |
memory_recall |
Recall relevant memories for a given context |
memory_stats |
Get knowledge graph statistics |
Examples
Once configured, Claude Code can use the tools naturally:
- "Remember that Alice is a senior engineer at Acme Corp"
- "What do you know about the payments project?"
- "List all the entities in my knowledge graph"
- "Create an entity for the new API gateway project with tags backend, infrastructure"
Environment Variables
| Variable | Default | Description |
|---|---|---|
MINDREADER_URL |
http://localhost:18900 |
MindReader API base URL |
MINDREADER_TOKEN |
(empty) | Bearer token for authentication |
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.